From Transkribus Wiki
Revision as of 12:37, 25 October 2019 by Sebastian Colutto (Talk | contribs)

Jump to: navigation, search

P2PaLA is a layout analysis tool that recognizes structure types on region level and baselines from a page based on pre-trained models.
The tool was developed by Lorenzo Quirós Díaz at the UPVLC in Valencia, see https://github.com/lquirosd/P2PaLA for the full Open Source codebase.


Currently, the recognition is integrated into the Transkribus expert client (TranskribusX) for pre-trained models.
In this process, the P2PaLA tool creates new text-regions from trained structure types and optionally also baselines contained in those regions.
The table shows detailed information on all available models.
The column "Structure types" shows the list of region types this model recognizes and the column "Baslelines" shows if this models was also trained to detect baselines.


Currently all pre-trained models are publicly available for all users. In a later stage of the integration, models will be associated with collections and users as with the HTR in Transkribus.
If you have your own dataset for training and recognition, please send us an E-Mail (email@transkribus.eu), then we can train a model for you.
Please make sure to tag structure types on region level only and avoid overlapping between different regions. Also specify if baseline detection should be trained too (which may only make sense for larger datsets). For structure type recognition, a training set of about 50-100 pages should be enough to generate a decent model, depending of course on the complexity of your layouts. Please note, that the tool can only recognize structure types that are in any way visually or positionally distinguishable on a page. Also note that P2PaLA is currently not a production-ready tool, thus please don't expect 'perfect' results.

Training Parameters

Structure types: these are the structure types that are tagged using Transkriubs on region level. Do not use whitespace in those structure types and be careful with case sensitivity. Merged structure types: if you want to treat certain structure types like other (e.g. footnote-continued or footer like footnote) then you can specify that here. Expected is a list of the structure types where other are merge into, separated by a colon, e.g.: 'footnote:footnote-continued,footer heading:header' whould mean that 'footnote-continue' and 'footnote' are regarded as 'footnote' while 'header' is regarded as 'heading'